Browsing by Author "Zhu, Yada"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Mastering Long-Tail Complexity on Graphs: Characterization, Learning, and Generalization
    Wang, Haohui; Jing, Baoyu; Ding, Kaize; Zhu, Yada; Cheng, Wei; Zhang, Si; Fan, Yonghui; Zhang, Liqing; Zhou, Dawei (ACM, 2024-08-25)
    In the context of long-tail classification on graphs, the vast majority of existing work primarily revolves around the development of model debiasing strategies, intending to mitigate class imbalances and enhance the overall performance. Despite the notable success, there is very limited literature that provides a theoretical tool for characterizing the behaviors of long-tail classes in graphs and gaining insight into generalization performance in real-world scenarios. To bridge this gap, we propose a generalization bound for long-tail classification on graphs by formulating the problem in the fashion of multi-task learning, i.e., each task corresponds to the prediction of one particular class. Our theoretical results show that the generalization performance of long-tail classification is dominated by the overall loss range and the task complexity. Building upon the theoretical findings, we propose a novel generic framework Hier- Tail for long-tail classification on graphs. In particular, we start with a hierarchical task grouping module that allows us to assign related tasks into hypertasks and thus control the complexity of the task space; then, we further design a balanced contrastive learning module to adaptively balance the gradients of both head and tail classes to control the loss range across all tasks in a unified fashion. Extensive experiments demonstrate the effectiveness of HierTail in characterizing long-tail classes on real graphs, which achieves up to 12.9% improvement over the leading baseline method in balanced accuracy.
  • Thumbnail Image
    TGEditor: Task-Guided Graph Editing for Augmenting Temporal Financial Transaction Networks
    Zhang, Shuaicheng; Zhu, Yada; Zhou, Dawei (ACM, 2023-11-27)
    Recent years have witnessed a growth of research interest in designing powerful graph mining algorithms to discover and characterize the structural pattern of interests from financial transaction networks, motivated by impactful applications including anti-money laundering, identity protection, product promotion, and service promotion. However, state-of-the-art graph mining algorithms often suffer from high generalization errors due to data sparsity, data noisiness, and data dynamics. In the context of mining information from financial transaction networks, the issues of data sparsity, noisiness, and dynamics become particularly acute. Ensuring accuracy and robustness in such evolving systems is of paramount importance. Motivated by these challenges, we propose a fundamental transition from traditional mining to augmentation in the context of financial transaction networks. To navigate this paradigm shift, we introduce TGEditor, a versatile task-guided temporal graph augmentation framework. This framework has been crafted to concurrently preserve the temporal and topological distribution of input financial transaction networks, whilst leveraging the label information from pertinent downstream tasks, denoted as T, inclusive of crucial downstream tasks like fraudulent transaction classification. In particular, to efficiently conduct task-specific augmentation, we propose two network editing operators that can be seamlessly optimized via adversarial training, while simultaneously capturing the dynamics of the data: Add operator aims to recover the missing temporal links due to data sparsity, and Prune operator is formulated to remove irrelevant/noisy temporal links due to data noisiness. Extensive results on financial transaction networks demonstrate that TGEditor 1) well preserves the data distribution of the original graph and 2) notably boosts the performance of the prediction models in the tasks of vertex classification and fraudulent transaction detection.